Skills
skills/certikdev/skills/skylens-transaction-analysis/Gen Agent Trust Hub

skylens-transaction-analysis

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection via untrusted blockchain data. \n
  • Ingestion points: scripts/skylens.py retrieves transaction traces and contract source code from the skylens.certik.com API. \n
  • Boundary markers: The skill does not provide instructions or delimiters to isolate untrusted data from the agent's core instructions. \n
  • Capability inventory: Includes the ability to write files to the local disk (via the --OUTPUT argument in get-source-file) and perform network requests. \n
  • Sanitization: No validation or filtering is performed on the data retrieved from the blockchain before presenting it to the agent.\n- [EXTERNAL_DOWNLOADS]: Fetches data from external vendor infrastructure. \n
  • The script scripts/skylens.py performs HTTPS requests to skylens.certik.com to fetch transaction details and source code as part of its core functionality.\n- [COMMAND_EXECUTION]: Local script execution with filesystem capabilities. \n
  • The skill executes a local Python script that can write files to the host filesystem when saving contract source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 06:13 AM